© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 222
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental and legal matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    89
    +0.11
    0.5%
    618
    +0.11
    0.5%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.05
    701
    +0.11
    0.04
    699
    +0.10
    0.03
    Negative Logits
     Compass
    -0.73
    velt
    -0.68
    GROUND
    -0.66
    kok
    -0.64
    IGHTS
    -0.64
     Directorate
    -0.62
     Balk
    -0.61
    ãĤ©
    -0.60
     Indra
    -0.59
    loo
    -0.59
    POSITIVE LOGITS
    nesota
    1.45
    iatures
    1.29
    neapolis
    1.25
    otaur
    1.17
    imize
    1.16
    isite
    1.16
    utes
    1.13
    erva
    1.00
    imal
    0.99
    ority
    0.98
    Activations Density 0.700%

    No Known Activations